Software Engineer

Job Title: Software Engineer

Location : Taipei, Taiwan

Role Overview:

We are seeking a highly skilled Software Engineer to troubleshoot and fix complex technical issues related to large-scale AI workloads on TPUs. This role focuses on distributed training, inference optimization, performance tuning, and debugging complex issues for production-grade AI systems.

You will work at the intersection of ML systems, distributed computing, and cloud infrastructure, enabling high-performance and cost-efficient LLM deployments.

You will partner closely with cross-functional, cross-regional teams to ensure our AI/ML infrastructure delivers exceptional value and drives success for our customers.

Key Responsibilities

Deep Technical Troubleshooting

· Reproduce complex customer issues in Google's internal environments

· Leverage AI to discover the root cause of a technical problem and verify it.

· Engage with partner engineering teams to understand how a complex system works.

LLM Deployment & Distributed Systems

· Load, configure, and deploy LLM models on TPU clusters at scale

· Work with frameworks such as JAX, Pytorch, or vLLM for large-scale model training and serving

· Design and manage distributed training strategies across multi-node environments

Performance Optimization

· Optimize LLM inference or training performance, autotuning scripts, and advanced TPU tuning techniques

· Improve throughput, latency, and cost efficiency for production AI workloads

· Identify and eliminate bottlenecks across compute, memory, and network layers

Kubernetes & Infrastructure Debugging

· Debug and optimize GKE / Kubernetes clusters for ML workloads

· Troubleshoot issues related to scheduling, networking, TPU utilization, and cluster performance

· Improve system reliability, scalability, and fault tolerance

Required Qualifications

· Bachelor’s or Master’s degree in Computer Science, Engineering, or related field

· Strong experience in troubleshooting complex technical problems that often require multiple iterations with partner teams or customers.

· Proven experience driving multi-team execution and a good team player.

· Operate effectively in fast-paced, ambiguous environments, bringing structure, prioritization, and clarity with minimal guidance.

· Strong programming skills in Python and/or C

Preferred Qualifications

· Strong experience in distributed systems and large-scale infrastructure

· Experience with Kubernetes (GKE preferred) and cluster debugging

· Familiarity with LLM

· Experience with GPU or TPU

· Experience with profiling tools (NCCL, DCGM, XLA profiling, etc.)

If you are interested in this position please share your updated resume with the details at rajat.singh@esolglobal.com

Current salary-

Expected salary-

Notice period-

Total years of experience-

Reason for job change-

Nationality-

Visa-